Predict and Eliminate EMI Signals for RF Shielding-Free MRI via Simultaneous Sensing and Deep Learning

Zhao, Yujiao; Xiao, Linfang; Liu, Yilong; Leong, Alex T. L.; Wu, Ed X.

doi:10.1109/apemc53576.2022.9888680

Cited by 2 publications

(16 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For each ULF MRI protocol, raw k‐space data were first processed for EMI removal through a k‐space deep learning scheme 10,12 and then reconstructed to two sets of 3D image data sets with 3‐mm isotropic resolution, Acq1 and Acq2, corresponding to NEX = 2. They were then fed into the model trained for specific contrast, producing one single superresolution 3D image data set with synthetic 1.5‐mm isotropic resolution.…”

Section: Methodsmentioning

confidence: 99%

“…Essential neuroimaging protocols have been successfully implemented and demonstrated on these ULF scanners, yielding clinically valuable information for stroke and tumor diagnosis within reasonable scan time, including use in intensive care units and coronavirus disease 2019 wards 6–8,10 . Recent developments also eliminate the need for traditional RF shielding room through active sensing and cancelation of electromagnetic interference (EMI) signals using analytical and deep learning approaches, 10–12 positioning ULF MRI for truly plug‐and‐scan point‐of‐care deployment. These advances demonstrate the clear potential to realize patient‐centric low‐cost shielding‐free MRI scanners and democratize MRI for low‐income and middle‐income countries.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution

Lau

Xiao

Zhao

et al. 2023

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

Recent development of ultra-low-field (ULF) MRI presents opportunities for low-power, shielding-free, and portable clinical applications at a fraction of the cost. However, its performance remains limited by poor image quality. Here, a computational approach is formulated to advance ULF MR brain imaging through deep learning of large-scale publicly available 3T brain data. Methods: A dual-acquisition 3D superresolution model is developed for ULF brain MRI at 0.055 T. It consists of deep cross-scale feature extraction, attentional fusion of two acquisitions, and reconstruction. Models for T 1 -weighted and T 2 -weighted imaging were trained with 3D ULF image data sets synthesized from the high-resolution 3T brain data from the Human Connectome Project.They were applied to 0.055T brain MRI with two repetitions and isotropic 3-mm acquisition resolution in healthy volunteers, young and old, as well as patients. Results:The proposed approach significantly enhanced image spatial resolution and suppressed noise/artifacts. It yielded high 3D image quality at 0.055 T for the two most common neuroimaging protocols with isotropic 1.5-mm synthetic resolution and total scan time under 20 min. Fine anatomical details were restored with intrasubject reproducibility, intercontrast consistency, and confirmed by 3T MRI. Conclusion:The proposed dual-acquisition 3D superresolution approach advances ULF MRI for quality brain imaging through deep learning of high-field brain data. Such strategy can empower ULF MRI for low-cost brain imaging, especially in point-of-care scenarios or/and in low-income and mid-income countries.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution

Lau

Xiao

Zhao

et al. 2023

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

show abstract

“…An active EMI elimination approach presents an alternative solution to remove EMI signals through active and simultaneous EMI sensing via multiple EMI sensing coils during scanning, and retrospective prediction and cancelation of EMI signals detected by MRI receive coil. [28][29][30][31][32][33][34][35] From an RF signal propagation point of view, relationships among EMI signals detected by various coils that are positioned and/or oriented differently can be well characterized by the electromagnetic coupling among coils. Such relationships allow EMI signals detected by the MRI receive coil to be predicted from EMI signals simultaneously acquired by one or multiple EMI sensing coils, thus enabling retrospective EMI cancelation through postprocessing.…”

Section: Introductionmentioning

confidence: 99%

“…In our recent work, a deep learning-based approach was developed to model and predict EMI signals from the acquired MRI receive coil signals. 19,34,35 In contrast to the analytical methods mentioned previously, this method assumes that the relationship between EMI signals detected by EMI sensing coils and MRI receive coil, although linear in theory, can be better approximated in practice through a versatile time domain convolution neural network (CNN) model that incorporates nonlinear operations. This assumption has been well supported by successful shielding-free 0.055T brain imaging of a cohort of about 100 healthy volunteers and patients in our laboratory, 19,34,35 leading to improved performance over the EDITER method.…”

Section: Introductionmentioning

confidence: 99%

“…Additionally, this method has also been demonstrated for a much higher frequency regime on a 1.5T MRI scanner with incomplete RF shielding. 34,35 Despite the success in predicting and retrospectively reducing EMI signals so far, the aforementioned methods 19,[29][30][31][32][33][34][35] are certainly inadequate to enable truly RF shielding-free MRI. In practice, EMI nature and behaviors can be extremely complex.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Robust EMI elimination for RF shielding‐free MRI through deep learning direct MR signal prediction

Zhao,

Xiao,

et al. 2024

Magnetic Resonance in Med

Self Cite

View full text Add to dashboard Cite

PurposeTo develop a new electromagnetic interference (EMI) elimination strategy for RF shielding‐free MRI via active EMI sensing and deep learning direct MR signal prediction (Deep‐DSP).MethodsDeep‐DSP is proposed to directly predict EMI‐free MR signals. During scanning, MRI receive coil and EMI sensing coils simultaneously sample data within two windows (i.e., for MR data and EMI characterization data acquisition, respectively). Afterward, a residual U‐Net model is trained using synthetic MRI receive coil data and EMI sensing coil data acquired during EMI signal characterization window, to predict EMI‐free MR signals from signals acquired by MRI receive and EMI sensing coils. The trained model is then used to directly predict EMI‐free MR signals from data acquired by MRI receive and sensing coils during the MR signal‐acquisition window. This strategy was evaluated on an ultralow‐field 0.055T brain MRI scanner without any RF shielding and a 1.5T whole‐body scanner with incomplete RF shielding.ResultsDeep‐DSP accurately predicted EMI‐free MR signals in presence of strong EMI. It outperformed recently developed EDITER and convolutional neural network methods, yielding better EMI elimination and enabling use of few EMI sensing coils. Furthermore, it could work well without dedicated EMI characterization data.ConclusionDeep‐DSP presents an effective EMI elimination strategy that outperforms existing methods, advancing toward truly portable and patient‐friendly MRI. It exploits electromagnetic coupling between MRI receive and EMI sensing coils as well as typical MR signal characteristics. Despite its deep learning nature, Deep‐DSP framework is computationally simple and efficient.

show abstract

Predict and Eliminate EMI Signals for RF Shielding-Free MRI via Simultaneous Sensing and Deep Learning

Cited by 2 publications

References 5 publications

Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution

Pushing the limits of low‐cost ultra‐low‐field MRI by dual‐acquisition deep learning 3D superresolution

Robust EMI elimination for RF shielding‐free MRI through deep learning direct MR signal prediction

Contact Info

Product

Resources

About